Assisted Landscape Design Model Based on Deep Lab v3+ and Computer Vision
Authors: 
Xiaoli He, Hong ZhangAuthors Info & Claims
Pages 32 - 36
Abstract
Abstract. Reasonable landscape design of urban public space is the key to urbanization transformation. In order to create a green, intelligent and humanistic urban image and enhance the overall beauty of the urban environment, the study provides an extraction method of landscape elements for landscape design with the help of computer vision detection technology and image segmentation model. The experimental results show that the method designed by the study has a better balance of precision and recall, with a precision of 0.9 and a recall of 0.97. The loss function curve of the method converges to a minimum value of 0.50, which is faster, and the average intersection and merger ratio reaches the level of 0.5 at the early iteration, which is better than other models. When applied to landscape design examples, the method performs well in terms of subjective evaluation indexes and panoramic quality compared to traditional design. The study of assisted landscape design method based on Deep Lab v3+ and computer vision provides new ideas for the digital transformation of landscape design, and provides theoretical support and technical guidance for the diversified and high-quality design needs of landscape design.
References
[1]
F. Tomatis, M. Egerer, A. Correa-Guimaraes, and L. M. Navas-Gracia, "Urban Gardening in a Changing Climate: A Review of Effects, Responses and Adaptation Capacities for Cities," Agriculture, vol. 13, no. 2, pp. 502-517, 2023.
[2]
M. El Ouardi, and F. Montambeault, "Collectively gardening the urban public space in Mexico City: When informal practices interact with the state," International Journal of Urban and Regional Research, vol. 47, no. 2, pp. 201-220, 2023.
[3]
E. Apostolopoulou, and P. Kotsila, "Community gardening in Hellinikon as a resistance struggle against neoliberal urbanism: spatial autogestion and the right to the city in post-crisis Athens, Greece," Urban Geography, vol. 43, no. 2, pp. 293-319, 2022.
[4]
M. A. Pham, S. B. Scott, L. R. Fyie, and M. M. Gardiner, "Sustainable landscaping programs in the United States and their potential to encourage conservation and support ecosystem services," Urban Ecosystems, vol. 25, no. 5, pp. 1481-1490, 2022.
[5]
J. Segar, C. T. Callaghan, E. Ladouceur, J. N. Meya, H. M. Pereira, A. Perino,and I. R. Staude, "Urban conservation gardening in the decade of restoration," Nature Sustainability, vol. 5, no. 8, pp. 649-656, 2022.
[6]
Z. Li, S. Zhang, and J. Dong, "Suggestive Data Annotation for CNN-Based Building Footprint Mapping Based on Deep Active Learning and Landscape Metrics," Remote Sensing, vol. 14, no. 13, pp. 3147-3163, 2022.
[7]
C. Yang, and T. Liu, "Social media data in urban design and landscape research: a comprehensive literature review," Land, vol. . 11, no. 10, pp. 1796-1817, 2022.
[8]
D. Wen, M. Liu, and Z. Yu, "Quantifying ecological landscape quality of urban street by open street view images: A case study of xiamen island, china," Remote Sensing, vol. 14, no. 14, pp. 3360-3377, 2022.
[9]
P. Hurtik, V. Molek, J. Hula, M. Vajgl, P. Vlasanek, and T. Nejezchleba, "Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3," Neural Computing and Applications, vol. 34, no. 10, pp. 8275-8290, 2022.
[10]
N. Khasawneh, M. Fraiwan, and L. Fraiwan, "Detection of K-complexes in EEG signals using deep transfer learning and YOLOv3," Cluster Computing, vol. 26, no. 6, pp. 3985-3995, 2023.
[11]
D. Jia, Z. He, C. Zhang, W. Yin, N. Wu, and Z. Li, "Detection of cervical cancer cells in complex situation based on improved YOLOv3 network, " Multimedia tools and applications, vol. 81, no. 6, pp. 8939-8961, 2022.
[12]
T. H. Liu, X. N. Nie, J. M. Wu, D. Zhang, W. Liu, Y. F. Cheng, and L. Qi, "Pineapple (Ananas comosus) fruit detection and localization in natural environment based on binocular stereo vision and improved YOLOv3 model," Precision Agriculture, vol. 24, no. 1, pp. 139-160, 2023.
[13]
M. Yaqub, F. Jinchao, S. Ahmed, A. Mehmood, I. S. Chuhan, M. A. Manan, and M. S. Pathan, "DeepLabV3, IBCO-based ALCResNet: a fully automated classification, and grading system for brain tumor," Alexandria Engineering Journal, vol. 76, no. 5, pp. 609-627, 2023.
[14]
S. Xiang, L. Wei, and K. Hu, "Lightweight colon polyp segmentation algorithm based on improved DeepLabV3," Journal of Cancer, vol. 15, no. 1, pp. 41-53, 2024.
[15]
D. Xi, Y. Qin, and Z. Wang, "Attention Deeplabv3 model and its application into gear pitting measurement," Journal of Intelligent & Fuzzy Systems, vol. 42, no. 4, pp. 3107-3120, 2022.
[16]
M. Haithami, A. Ahmed, I. Y. Liao, and H. Jalab, "Employing GRU to combine feature maps in DeeplabV3 for a better segmentation model. " Nordic Machine Intelligence, vol. 1, no. 1, pp. 29-31, 2021.
Index Terms
- Assisted Landscape Design Model Based on Deep Lab v3+ and Computer Vision
Index terms have been assigned to the content through auto-classification.
Recommendations
The Landscape from Architecture to the City: Strategies and Methods to Regenerate Through Design
Computational Science and Its Applications – ICCSA 2024 WorkshopsAbstractThe contribution intends to propose an innovative and transdisciplinary approach to restore centrality to the landscape in the process of urban regeneration. The urban landscape, in its naturalistic-environmental dimension, is an essential part of ...
The Integration of Chinese Painting Aesthetics and Landscape Design
ICETCE '12: Proceedings of the 2012 Second International Conference on Electric Technology and Civil EngineeringThe diversified development of world economy has been driven cultural changed and impacted to landscape design. From the late twentieth Century landscape design concept has an obvious transition from early emphasis function to form evolution. Since ...
Research on Intelligent Landscape Design Based on Distributed Integrated Model
Traditional landscape design methods rely entirely on the experience of designers and are difficult to adapt to the needs of modern society. This article proposes a landscape design method based on a distributed integrated model. Based on landscape ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
April 2024
379 pages
ISBN:9798400709777
DOI:10.1145/3653644
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 20 September 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
FAIML 2024
FAIML 2024: 2024 3rd International Conference on Frontiers of Artificial Intelligence and Machine Learning
April 26 - 28, 2024
Yichang, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 9Total Downloads
- Downloads (Last 12 months)9
- Downloads (Last 6 weeks)6
Reflects downloads up to 20 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format